EvalEval Coalition

AI & ML interests

We’re building a research coalition on evaluating evaluations (EvalEval)! Hosted by Hugging Face, University of Edinburgh, and EleutherAI.

Recent Activity

EvalEvalBot  new activity about 15 hours ago

evaleval/EEE_datastore:[Submission] Terminal-Bench 2.0 leaderboard data (schema v0.2.2, eval_library=harbor)

EvalEvalBot  new activity 7 days ago

evaleval/EEE_datastore:Upload 5 files

EvalEvalBot  new activity 7 days ago

evaleval/EEE_datastore:Upload 5 files

View all activity

Team members 33